ROBOSHACKLES is a new safety dataset for embodied foundation models created through a pipeline of hazard-aware editing and video synthesis from real observations, with all six tested models generating unsafe actions at a 100% rate.
Zico Kolter and Hamed Hassani and George J
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
X-Safe masks actions in configuration space using forward kinematics and quasi-static object models to give probabilistic collision-avoidance guarantees that transfer across robot embodiments without per-setup engineering.
citing papers explorer
-
ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models
ROBOSHACKLES is a new safety dataset for embodied foundation models created through a pipeline of hazard-aware editing and video synthesis from real observations, with all six tested models generating unsafe actions at a 100% rate.
-
Any-Body Guard: Universal Safeguarding for Manipulation Policies via Action Masking
X-Safe masks actions in configuration space using forward kinematics and quasi-static object models to give probabilistic collision-avoidance guarantees that transfer across robot embodiments without per-setup engineering.